← Back to Skills Marketplace
222
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install fun-asr
Description
阿里云百炼 FunASR 录音文件识别，使用阿里云 DashScope API 进行语音转文字。当用户需要转录音频文件时触发。
README (SKILL.md)
Fun-ASR
Fun-ASR 是通义实验室百聆团队推出的端到端语音识别大模型，是基于数千万小时真实语音数据训练而成，具备强大的上下文理解能力与行业适应性。
激活条件
| 触发场景 | 说明 |
|---|---|
| 用户发送音频文件 | .wav / .mp3 / .m4a / .flac / .ogg 等格式 |
| 用户要求转录 | "转写音频"、"语音转文字" |
| 音频文件处理 | 需要提取音频中的文字内容 |
配置
设置环境变量：
export DASHSCOPE_API_KEY="sk-xxx"
使用方法
安装依赖
pip install dashscope librosa
转写音频文件
python scripts/cli.py audio.wav
版本：1.0.0 创建于：2026-03-16
Usage Guidance
This skill appears to be a small client for Aliyun DashScope ASR and will send any audio you run through it to DashScope's service (wss://dashscope.aliyuncs.com). Before installing or running: 1) Treat DASHSCOPE_API_KEY as a secret — the registry metadata failed to declare it, so do not paste keys into unfamiliar installs. 2) Only use a minimally scoped or ephemeral API key and avoid transcribing sensitive audio. 3) The package includes .claude/settings.local.json permitting WebFetch to bailian.console.aliyun.com (an unrelated Aliyun console domain) — consider removing or reviewing that file if you don't want the skill to request web access. 4) Verify the source/owner since source/homepage are unknown; inspect the dashscope Python package and network endpoints you will be talking to. 5) If you plan to install, run in an isolated environment (virtualenv/container) and confirm the DASHSCOPE API key usage is acceptable.
Capability Analysis
Type: OpenClaw Skill
Name: fun-asr
Version: 1.0.0
The skill bundle is a legitimate implementation for transcribing audio files using the Alibaba DashScope FunASR API. The Python script (scripts/cli.py) correctly handles audio processing via librosa and communicates with the official Alibaba WebSocket endpoint (dashscope.aliyuncs.com) without any signs of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
The code and SKILL.md implement an Aliyun DashScope-based ASR client (reads an audio file and sends PCM to a DashScope websocket). That matches the skill description. However registry metadata lists no required environment variables while both SKILL.md and the script require DASHSCOPE_API_KEY, an omission that is incoherent.
Instruction Scope
Runtime instructions are limited to installing two Python packages, setting DASHSCOPE_API_KEY, and running scripts/cli.py on an audio file. The script only reads the provided audio file and sends audio frames to DashScope; it does not attempt to read unrelated files, other credentials, or system state.
Install Mechanism
There is no install spec in the registry (instruction-only), and the SKILL.md instructs pip installing dashscope and librosa. No downloads from arbitrary URLs or archive extraction are present. The only code file is a small CLI script that uses those libraries.
Credentials
The script and SKILL.md require DASHSCOPE_API_KEY (used as dashscope.api_key), but the skill's declared required env vars list is empty — this mismatch could mislead users about secret requirements. Also the included .claude/settings.local.json grants WebFetch to bailian.console.aliyun.com which is unrelated to the runtime websocket endpoint (wss://dashscope.aliyuncs.com) and is not explained.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system-wide privileges. It does not modify other skills' configs. Including a settings.local.json is benign but its allowed WebFetch domain is unexpected.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install fun-asr - After installation, invoke the skill by name or use
/fun-asr - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of fun-asr skill:
- Integrates Aliyun DashScope API for automatic speech recognition of audio files.
- Supports various audio formats including .wav, .mp3, .m4a, .flac, and .ogg.
- Automatically activates when users request audio transcription or send audio files.
- Provides setup instructions, including API key configuration and Python dependency installation.
- Includes command-line usage example for transcribing audio files.
Metadata
Frequently Asked Questions
What is Fun-ASR speech recognition?
阿里云百炼 FunASR 录音文件识别，使用阿里云 DashScope API 进行语音转文字。当用户需要转录音频文件时触发。 It is an AI Agent Skill for Claude Code / OpenClaw, with 222 downloads so far.
How do I install Fun-ASR speech recognition?
Run "/install fun-asr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Fun-ASR speech recognition free?
Yes, Fun-ASR speech recognition is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Fun-ASR speech recognition support?
Fun-ASR speech recognition is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Fun-ASR speech recognition?
It is built and maintained by 彭震东 (@pengzhendong); the current version is v1.0.0.
More Skills